提交 f8096783 编写于 作者: Y Yufen Yu 提交者: Yang Yingliang

block: fix use-after-free on cached last_lookup partition

hulk inclusion
category: bugfix
bugzilla: 27962
CVE: NA
---------------------------

delete_partition() clears the cached last_lookup partition. However
the .last_lookup cache may be overwritten by one IO path after
it is cleared from delete_partition(). Then another IO path may
use the cached deleting partition after __delete_partition() is
called, then use-after-free is triggered on the cached partition.

Fixes the issue by the following approach:

1) always get the partition's refcount via hd_struct_try_get() before
setting .last_lookup

2) move clearing .last_lookup from delete_partition() to
__delete_partition() which is release handle of the partition's
percpu-refcount, so that no IO path can overwrite .last_lookup after it
is cleared in __delete_partition().

It is one candidate approach of Yufen's patch[1] which adds overhead
in fast path by indirect lookup which may introduce one extra cacheline
in IO path. Also this patch relies on percpu-refcount's protection, and
it is easier to understand and verify.

[1] https://lore.kernel.org/linux-block/20200109013551.GB9655@ming.t460p/T/#tReported-by: NYufen Yu <yuyufen@huawei.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Conflict:
	include/linux/genhd.h
	block/blk-core.c
Signed-off-by: NYufen Yu <yuyufen@huawei.com>
Reviewed-by: NHou Tao <houtao1@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>
上级 dc1ae2ee
......@@ -2788,18 +2788,6 @@ void blk_account_io_start(struct request *rq, bool new_io)
part_stat_inc(cpu, part, merges[rw]);
} else {
part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
if (!hd_struct_try_get(part)) {
/*
* The partition is already being removed,
* the request will be accounted on the disk only
*
* We take a reference on disk->part0 although that
* partition will never be deleted, so we can treat
* it as any other partition.
*/
part = &rq->rq_disk->part0;
hd_struct_get(part);
}
part_round_stats(rq->q, cpu, part);
part_inc_in_flight(rq->q, part, rw);
rq->part = part;
......
......@@ -272,17 +272,21 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
ptbl = rcu_dereference(disk->part_tbl);
part = rcu_dereference(ptbl->last_lookup);
if (part && sector_in_part(part, sector))
if (part && sector_in_part(part, sector) && hd_struct_try_get(part))
return part;
for (i = 1; i < ptbl->len; i++) {
part = rcu_dereference(ptbl->part[i]);
if (part && sector_in_part(part, sector)) {
if (!hd_struct_try_get(part))
goto exit;
rcu_assign_pointer(ptbl->last_lookup, part);
return part;
}
}
exit:
hd_struct_get(&disk->part0);
return &disk->part0;
}
EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
......
......@@ -263,6 +263,12 @@ static void delete_partition_work_fn(struct work_struct *work)
void __delete_partition(struct percpu_ref *ref)
{
struct hd_struct *part = container_of(ref, struct hd_struct, ref);
struct disk_part_tbl *ptbl =
rcu_dereference_protected(part->disk->part_tbl, 1);
rcu_assign_pointer(ptbl->last_lookup, NULL);
put_device(disk_to_dev(part->disk));
INIT_RCU_WORK(&part->rcu_work, delete_partition_work_fn);
queue_rcu_work(system_wq, &part->rcu_work);
}
......@@ -284,8 +290,9 @@ void delete_partition(struct gendisk *disk, int partno)
if (!part)
return;
get_device(disk_to_dev(disk));
rcu_assign_pointer(ptbl->part[partno], NULL);
rcu_assign_pointer(ptbl->last_lookup, NULL);
kobject_put(part->holder_dir);
device_del(part_to_dev(part));
......@@ -350,6 +357,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
p->nr_sects = len;
p->partno = partno;
p->policy = get_disk_ro(disk);
p->disk = disk;
if (info) {
struct partition_meta_info *pinfo = alloc_part_info(disk);
......
......@@ -129,6 +129,7 @@ struct hd_struct {
struct disk_stats dkstats;
#endif
struct percpu_ref ref;
struct gendisk *disk;
struct rcu_work rcu_work;
KABI_RESERVE(1)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册